Create Dockerfile

Dockerfile

@@ -0,0 +1,18 @@
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("dphn/Dolphin3.0-Mistral-24B")
+model = AutoModelForCausalLM.from_pretrained("dphn/Dolphin3.0-Mistral-24B")
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+inputs = tokenizer.apply_chat_template(
+	messages,
+	add_generation_prompt=True,
+	tokenize=True,
+	return_dict=True,
+	return_tensors="pt",
+).to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=40)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))